Intent Tagging: Exploring Micro-Prompting Interactions for Supporting Granular Human-GenAI Co-Creation Workflows

2025-02-26

AI Summary

Generative AI faces three core challenges in creative content creation: poor intent alignment, ambiguous prompt construction, and weak workflow integration. To address these, this paper introduces IntentTagger—a novel system that pioneers an “intent tag”-driven micro-prompt interaction paradigm. Intent tags decompose user intent into fine-grained, atomic units, enabling nonlinear, traceable human-AI collaboration in slide authoring. The system integrates intent modeling, micro-prompt engineering, and tag-based UI design. A qualitative study with 12 participants demonstrates that intent tags significantly enhance expressive flexibility and AI response relevance. The study further reveals the utility of vague intent expression and meta-intent guidance. Based on empirical findings, we distill seven evidence-informed design principles for GenAI-supported creative authoring.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Despite Generative AI (GenAI) systems' potential for enhancing content creation, users often struggle to effectively integrate GenAI into their creative workflows. Core challenges include misalignment of AI-generated content with user intentions (intent elicitation and alignment), user uncertainty around how to best communicate their intents to the AI system (prompt formulation), and insufficient flexibility of AI systems to support diverse creative workflows (workflow flexibility). Motivated by these challenges, we created IntentTagger: a system for slide creation based on the notion of Intent Tags - small, atomic conceptual units that encapsulate user intent - for exploring granular and non-linear micro-prompting interactions for Human-GenAI co-creation workflows. Our user study with 12 participants provides insights into the value of flexibly expressing intent across varying levels of ambiguity, meta-intent elicitation, and the benefits and challenges of intent tag-driven workflows. We conclude by discussing the broader implications of our findings and design considerations for GenAI-supported content creation workflows.

Problem

• Improves Human-GenAI co-creation workflows
• Addresses misalignment in AI-generated content
• Enhances prompt formulation flexibility

Innovation

• Intent Tags for granular workflows
• Micro-prompting for user intent
• Flexible Human-GenAI co-creation